CORRELATION AND TAIL DEPENDENCE ANALYSIS IN PARALLEL COORDINATES
Parallel Coordinates (PC) provide an alternative visualization of data constructed by embedding the parallel axes vertically in Cartesian Coordinates (CC) system. By using PC, we may be able to observe multivariate data behavior easier and more accurately, in particular, via dependence pattern....
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/33934 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Parallel Coordinates (PC) provide an alternative visualization of data constructed
by embedding the parallel axes vertically in Cartesian Coordinates (CC) system.
By using PC, we may be able to observe multivariate data behavior easier and more
accurately, in particular, via dependence pattern.
In this thesis, we emphasize on visualization of correlation and multivariate
tail dependence in PC. Specically, we analyze and identify their behavior through
data. Furthermore, we propose a method of determining appropriate tail dependence
coecient by preserving Pearsons correlation coecient in upper tail of the data. |
|---|